Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4478 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2817. Min Range: -6.2817
Max Act: 6.2817. Min Act: -0.1700
Data Index: 121136 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2817. Min Range: -6.2817
Max Act: 6.1879. Min Act: -0.1700
Data Index: 3804411 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2817. Min Range: -6.2817
Max Act: 6.1254. Min Act: -0.1700
Data Index: 7441479 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2817. Min Range: -6.2817
Max Act: 6.0629. Min Act: -0.1700
Data Index: 1344600 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2817. Min Range: -6.2817
Max Act: 6.0317. Min Act: -0.1700
Data Index: 3772124 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2817. Min Range: -6.2817
Max Act: 5.9379. Min Act: -0.1700
Data Index: 7288383 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2817. Min Range: -6.2817
Max Act: 5.9692. Min Act: -0.1700
Data Index: 6288785 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2817. Min Range: -6.2817
Max Act: 5.8754. Min Act: -0.1700
Data Index: 1438927 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2817. Min Range: -6.2817
Max Act: 5.8754. Min Act: -0.1700
Data Index: 7439182 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2817. Min Range: -6.2817
Max Act: 5.9067. Min Act: -0.1700
Data Index: 4749641 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2817. Min Range: -6.2817
Max Act: 5.8754. Min Act: -0.1700
Data Index: 3527924 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2817. Min Range: -6.2817
Max Act: 5.8754. Min Act: -0.1700
Data Index: 2948397 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2817. Min Range: -6.2817
Max Act: 5.8442. Min Act: -0.1700
Data Index: 2071784 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2817. Min Range: -6.2817
Max Act: 5.8442. Min Act: -0.1700
Data Index: 4772119 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2817. Min Range: -6.2817
Max Act: 5.7817. Min Act: -0.1700
Data Index: 7716761 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2817. Min Range: -6.2817
Max Act: 5.8442. Min Act: -0.1700
Data Index: 4597310 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2817. Min Range: -6.2817
Max Act: 5.8129. Min Act: -0.1700
Data Index: 4399371 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2817. Min Range: -6.2817
Max Act: 5.7817. Min Act: -0.1700
Data Index: 7103407 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2817. Min Range: -6.2817
Max Act: 5.7817. Min Act: -0.1700
Data Index: 4769377 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2817. Min Range: -6.2817
Max Act: 5.7817. Min Act: -0.1700
Data Index: 6361689 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19